Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     agenda
    -0.07
     nó
    -0.07
     rocking
    -0.07
     Worship
    -0.06
    bd
    -0.06
     плен
    -0.06
     VID
    -0.06
    odes
    -0.06
    ляд
    -0.06
     pan
    -0.06
    POSITIVE LOGITS
     ทำ
    0.07
    幹線
    0.07
    -founded
    0.06
     Diabetes
    0.06
     dific
    0.06
    	max
    0.06
     normalize
    0.06
    entence
    0.06
    ра�
    0.06
    _bit
    0.06
    Act Density 0.008%

    No Known Activations